楼栋地址库的生成方法、装置、计算机设备及存储介质

By identifying building blocks and logistics addresses in images of target buildings, and generating a building address database using geographic coordinates and address correlation rules, the problem of address classification difficulties in existing technologies is solved, and a more efficient address database construction is achieved.

CN117633215BActive Publication Date: 2026-07-17丰图科技(深圳)有限公司

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
丰图科技(深圳)有限公司
Filing Date
2022-08-19
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

When building an address database, existing technologies struggle to determine the relationships between similar addresses, leading to difficulties in address classification and further increasing the complexity of address database construction.

Method used

By acquiring images of the target building, the building block it is located on is determined, and the logistics addresses and suspected logistics addresses of the target building block are identified in the historical logistics addresses within the target area. Address classification is performed using geographic coordinate information and address correlation rules to generate a building address database.

Benefits of technology

This reduces the difficulty of address classification, improves the efficiency of address database construction, and ensures the accuracy and completeness of the address database.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117633215B_ABST
    Figure CN117633215B_ABST
Patent Text Reader

Abstract

本申请公开了一种楼栋地址库的生成方法、装置、计算机设备及存储介质,方法包括:在包含有目标楼栋的目标图像中,确定目标楼栋所在的目标楼块面;在目标区域内的多个历史物流地址中,确定目标楼块面中的多个目标物流地址、疑似物流地址;根据疑似物流地址、目标物流地址以及目标楼栋对应的楼栋名称,生成目标楼栋对应的地址库。本申请实施例通过获取楼栋的楼块面,将楼块面中的地址以及疑似物流地址均分类至该楼块面,并生成楼栋地址库,在此过程中,无需确定相似的地址所属类别是否相同以生成各个类别,相较于仅根据地址的文本信息进行地址的无监督分类,基于楼块面来进行地址分类的难度更低,从而降低了构建地址库的难度。
Need to check novelty before this filing date? Find Prior Art